Farview: Disaggregated Memory with Operator Off-loading for Database Engines

TL;DR

Farview introduces a disaggregated memory system for databases using FPGA-based smart NICs, enabling remote DRAM access and operator offloading, which improves flexibility and performance in cloud database deployments.

Contribution

This paper presents Farview, a novel disaggregated memory solution with operator offloading capabilities implemented on FPGA-based smart NICs for database systems.

Findings

Farview performs comparably to local buffer caches across workloads.

It outperforms local caches in certain analytical query scenarios.

Disaggregated memory with operator offloading is viable for cloud databases.

Abstract

Cloud deployments disaggregate storage from compute, providing more flexibility to both the storage and compute layers. In this paper, we explore disaggregation by taking it one step further and applying it to memory (DRAM). Disaggregated memory uses network attached DRAM as a way to decouple memory from CPU. In the context of databases, such a design offers significant advantages in terms of making a larger memory capacity available as a central pool to a collection of smaller processing nodes. To explore these possibilities, we have implemented Farview, a disaggregated memory solution for databases, operating as a remote buffer cache with operator offloading capabilities. Farview is implemented as an FPGA-based smart NIC making DRAM available as a disaggregated, network attached memory module capable of performing data processing at line rate over data streams to/from disaggregated memory. Farview supports query offloading using operators such as selection, projection, aggregation, regular expression matching and encryption. In this paper we focus on analytical queries and demonstrate the viability of the idea through an extensive experimental evaluation of Farview under different workloads. Farview is competitive with a local buffer cache solution for all the workloads and outperforms it in a number of cases, proving that a smart disaggregated memory can be a viable alternative for databases deployed in cloud environments.